Results for “model”

Journal articles (OpenAlex) Trinette Wright, Gabriel Ng, Shannon McInnes et al. · Scientific Reports Gadgets

Expanding access to spine surgery simulation through smartphone-based augmented reality

This study presents the development and validation of a low-cost, portable augmented reality (AR) simulator for screw placement training in the spine. Designed to operate on existing smart devices, the system uses image-based tracking to overlay virtual anatomical structures, landmarks, ideal screw placements and trajectories, and surgical tool animations onto 3D-printed vertebrae, eliminating the need for external tracking hardware or head-mounted displays. Vertebral models…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Fatma Aslı Kelkitli · International Journal of Sport Policy and Politics Geopolitics

Sports diplomacy sources of middle powers: the cases of Iran, Saudi Arabia and Türkiye

This article examines and compares sports diplomacy sources of Iran, Saudi Arabia and Türkiye with the aid of Joseph Nye’s soft power framework. These three states are middle powers with different political models in the Middle East. Iran presents itself as a religious democracy, Saudi Arabia promotes moderate Islam, while Türkiye positions itself as a conservative democracy. Experiencing problems to live up to the values they endorse at home, Tehran, Riyadh and Ankara…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Paul-Henri Francis Patrice Perrain · Problems of Post-Communism Geopolitics

Orthodoxy, Politics, and Kirillism: Reassessing Post-Soviet Church-State Symphonia in Patriarch Kirill’s Russia

After 1991, the Russian Orthodox Church (ROC) and the Kremlin agreed to reestablish cordial relations while mutually committing not to interfere in each other’s affairs. This model of church-state relations – referred to as symphonia – appears to be outdated under Patriarch Kirill. Drawing on the two priorities articulated by Kirill upon his election in 2009, this paper argues that the ROC has successfully penetrated the political sphere. It therefore proposes replacing the…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Wenping Gong, Han Gao · Urban Studies Geopolitics

Planning the post-socialist ‘in-betweenness’: Emergence of an authoritarian post-political planning model in Great Stone Industrial Park

Situated within the discourse of post-socialist urbanism, this study investigates the interstitial ‘in-betweenness’ of Belarus to conceptualize the emergence of an ‘authoritarian post-political planning’ model. Through an empirical analysis of the China-Belarus Great Stone Industrial Park, we examine how the authoritarian state appropriates post-political governance to integrate transnational capital and ensure regime survival. Drawing on discourse analysis and in-depth…

Read at Journal articles (OpenAlex)

arXiv (research papers) Wujie Xiong SI

Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection

Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later privileged actions. Existing defenses mainly classify untrusted content or authorize proposed operations. They do not directly address how an agent's future authority should change once untrusted data enters its state. We present SkillGuard, a harness-level enforcement layer that treats this event as contamination and restricts…

Read at arXiv (research papers)

arXiv (research papers) Xun Wang SI

AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes

Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to save deployment costs. All existing audits decide backbone identity from the text-output channel, which is structurally fragile for agentic APIs because modern serving stacks (OpenAI, Anthropic, Gemini, Cloudflare Workers AI, LangGraph) discard text and expose only structured actions when the model calls a tool, and…

Read at arXiv (research papers)

arXiv (research papers) Zhenhua Zou SI

AgentKernel: The Trust-Native Agentic Operating System

Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate beliefs in long-term memory, and invoke privileged tools. This creates an attack surface in which malicious payloads can enter through model inputs and cause harmful tool actions. Yet current governance stacks remain application-level middleware that share a process trust boundary with the agents they monitor. We argue that agents…

Read at arXiv (research papers)

arXiv (research papers) Yupei Liu SI

LongPIBench: A Long-Context Benchmark for Prompt Injection

Prompt injection attacks pose a serious security risk to large language models in real-world applications. However, existing prompt injection benchmarks primarily focus on short-context inputs, leaving the attacks and defenses in long-context settings largely unexplored. This gap leads to a substantial overestimation of the effectiveness of current defenses. In this paper, we bridge the gap by introducing LongPIBench, a long-context benchmark for prompt injection covering 4…

Read at arXiv (research papers)

arXiv (research papers) Zi Liang SI

CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?

Prompt injection attacks on Large Language Model (LLM) agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underlying LLMs to execute harmful actions outside their benign scope. While current defenses effectively counter known injection attacks, deploying them in LLM agent environments remains challenging due to attack variants and emerging threats. Moreover, existing solutions typically suffer from an…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ricardo E. Sánchez-Piedrahita, Jairo R. Coronado-Hernández, Germán Herrera Vidal et al. · Supply Chain Analytics Geopolitics

An analytical framework for modeling security and drug trafficking supply chains as a complex system

Maritime drug trafficking in the Colombian Caribbean exhibits structural properties of a Complex Adaptive System (CAS), characterized by decentralized, evolving, and non-linear interactions. This study establishes a systems-based framework to analyze the adaptive behavior of illicit maritime logistics and extract intelligence for risk-based interdiction. A ten-attribute instrument was designed to quantify CAS dimensions, applied to a sample of 223 experts from military…

Read at Journal articles (OpenAlex)

Phenomenal World Fernando Rugitsky Geopolitics

Against the Lewis Model

The work of Arthur Lewis is one the best entry points for an engagement with classic development thinking. In his biography of the Caribbean economist, Robert Tignor argued that “Economic Development With Unlimited Supplies of Labor,” Lewis’s classic 1954 article, “galvanized the new field of development economics, providing it with a legitimacy that it had

Read at Phenomenal World

arXiv (research papers) Md Habibur Rahman SI

The Framing Gap: Indirect Prompt-Injection Exfiltration Defeats Surface-Level Defenses in Tool-Using Agents

A tool-using LLM agent that reads attacker-controlled web content while holding a secret faces indirect prompt injection: the content may make it exfiltrate the secret. In a safe synthetic lab (canary secret, mock tools, matched clean-vs-poisoned metric) we report the framing gap: across six models, ten overt injection classes are refused (gpt-4o 0%), but reframing the identical leak as a mandatory integrity signature, config field, or look-alike "trusted" host drives gpt-4o…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ahmad Jahed Mushtaq · Journalism Geopolitics

Investigating under fire: Journalistic challenges in Afghanistan’s Republic era (2001–2021)

Investigative journalism plays a vital role in exposing wrongdoing. This study examines the practices and challenges of investigative reporting in Afghanistan during the Republic era (2001–2021). Drawing on in-depth interviews with fifteen investigative journalists from leading television networks, it applies the Hierarchy of Influences model to analyze how multiple levels of pressure shaped investigative reporting in a conflict-affected context. The findings reveal that…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Quoc Dung Ngo, Vu Hiep Hoang · Corporate Governance Geopolitics

Anticipatory governance and stakeholder engagement in financial crisis management: evidence from Vietnam’s banking sector

Purpose This study aims to examine how anticipatory governance mechanisms and stakeholder engagement influence government bailout effectiveness and financial market stability during banking crises, with particular focus on implications for commercial bank board oversight and internal risk management frameworks. Design/methodology/approach Partial least squares structural equation modelling analysed survey data from 237 Vietnamese stakeholders, comprising financial experts…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Iván Ortiz-Garcés, Roberto Andrade · Future Internet Gadgets

Security-by-Design and Risk-Based Certification for AI-Enabled Smart Home

The integration of Artificial Intelligence (AI) into Internet of Things (IoT) ecosystems has enabled the development of advanced cyber–physical systems, including smart appliances, while introducing security, privacy, and AI governance risks that extend beyond the scope of traditional threat models. Existing approaches often address cybersecurity, AI risk management, and regulatory compliance in isolation, leaving manufacturers without a systematic method for translating…

Read at Journal articles (OpenAlex)

arXiv (research papers) Lin-Fa Lee SI

WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents

The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent execution into a browser security model centered on the Same-Origin Policy (SOP) leaves insufficient provenance and lifecycle guarantees for agent-accessible tools, creating three risks: subject-attribution spoofing, uncontrolled tool lifecycles, and semantic prompt injection. We propose WebMCP-Phalanx, a dual-layer agent…

Read at arXiv (research papers)

arXiv (research papers) Joshua Penman SI

Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors

Everything a language model sees is tokens. The serving stack knows what each span is -- user input, tool output, instructions -- but the model must keep track of that itself, and can lose track or be confused: text can be written to read like anything. Prompt injection is a natural exploit of this phenomenon. By scrambling the model's understanding of span identity, an attacker can induce unwanted and dangerous actions. Adding a non-textual channel to the model's input -- a…

Read at arXiv (research papers)

arXiv (research papers) Avital Aviv SI

Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2)

The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven shopping agents to authorize and execute payments on behalf of users. Its signed Checkout and Payment Mandates protect the integrity of transaction data after signing. Agent interactions and external inputs that shape a transaction before authorization remain outside that protection, including Agent-to-Agent Protocol (A2A) messages and Model Context Protocol (MCP) tool calls…

Read at arXiv (research papers)

arXiv (research papers) Trung-Anh Dang SI

GAP-Prompt: Gated Adaptive Prompting for Efficient Continual Learning

Continual learning faces the persistent challenge of catastrophic forgetting, where sequential task updates degrade previously acquired knowledge. While prompt-based methods integrated with pre-trained models offer a compelling solution by freezing the backbone, they often rely on static, task-level prompting strategies that overlook fine-grained intra-task diversity. In this paper, we propose Gated Adaptive Prompting (GAP-Prompt), a novel method that introduces…

Read at arXiv (research papers)

arXiv (research papers) Mehrdad Rostamzadeh SI

TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers

The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness introduces a severe server-side threat we term TrustShift: a compromised MCP server behaves benignly during an initial conditioning phase, building operational reliance and suppressing agent skepticism, before switching to an adversarial payload once an interaction threshold is reached. The evasion is temporal, not syntactic…

Read at arXiv (research papers)

Journal articles (OpenAlex) Haedo Cho, Chelsey Campillo Rodriguez, Patrick Slade · Frontiers in Digital Health Gadgets

Comparison of smartwatch-derived energy expenditure estimation during outdoor activities

BACKGROUND Smartwatches are commonly used to estimate energy expenditure, but studies have reported errors of 25% to 70%. The large range in estimation accuracy may be due to numerous factors, such as activity type, use case, and sensor data. We evaluated the differences in energy expenditure estimation among different smartwatches and models to identify the optimal use cases to achieve minimal error. OBJECTIVE We systematically evaluated the impact of different sensor…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jiahao Chen SI

Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds

Large Language Models (LLMs) have been integrated into complex ecosystems (e.g., Code Agents), while Indirect Prompt Injection (IPI) attacks have emerged as critical barriers to their safe deployment. Attackers exploit LLMs' indistinguishability between "instructions" and "data" to manipulate LLMs via maliciously injected instructions. Existing defenses, however, face an intractable safety-utility trade-off: most guardrails either incur high latency or suffer from severe…

Read at arXiv (research papers)

arXiv (research papers) Ziliang Zhang SI

Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for combining large language models (LLMs) with external knowledge sources. However, RAG systems remain vulnerable to prompt injection attacks, which may mislead the retriever or generator to expose sensitive database contents. To address this issue, we propose KFS-RAG, a defense that mitigates information leakage by reformulating the retrieved context. Specifically, our method first identifies a small…

Read at arXiv (research papers)

arXiv (research papers) Bohao Liao SI

TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents

Networked large language model (LLM) agents retrieve information from email, cloud storage, calendars, transaction platforms, and Web services to complete multistep tasks that produce persistent external effects. The same content needed for legitimate execution may also contain indirect prompt injections that redirect tool use, alter sensitive arguments, or disrupt task completion. Existing defenses mainly constrain untrusted content or individual tool calls, leaving user…

Read at arXiv (research papers)

arXiv (research papers) Roshan Sood SI

COPA: Continual Preference Optimization for Adaptive Prompt Injection Defense

LLMs remain vulnerable to prompt injection attacks, where adversarial instructions embedded in user inputs or external content manipulate model behavior and bypass safeguards. Existing defenses are predominantly static, relying on fixed alignment objectives or attack-specific filtering mechanisms that require redesign as new attack strategies emerge. While recent lifelong alignment methods address shifting user preferences, they do not account for adaptive adversaries that…

Read at arXiv (research papers)

arXiv (research papers) Rabimba Karanjai Larry SI

PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance

Autonomous AI agents are emerging as interfaces for decentralized finance (DeFi) actions such as swaps, lending operations, and yield management. Because these agents rely on large language models (LLMs) to plan transactions, they inherit the LLM's susceptibility to prompt injection and lack of mechanisms to bind a verifier's approval to the exact transaction ultimately submitted on-chain. We present PACE (Policy-Attested Contract Execution), a transaction-level…

Read at arXiv (research papers)

Journal articles (OpenAlex) Hao Chen, Meg Rithmire · Asian Economic Policy Review Geopolitics

China's Diffusion‐Forward AI Strategy: The “ AI Race” in Political Economic Context

ABSTRACT The United States and China are pursuing fundamentally different artificial intelligence strategies, a divergence that has been largely obscured by the prevailing focus on large language model competition and frontier model capabilities. Drawing on official policy documents, original registration data for generative AI services in China, and a patent‐based case study of humanoid robotics firm UBTECH, this paper documents China's “diffusion‐forward” strategy: a…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jiawei Liu SI

Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation

Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection, backdoors, poisoning, or adversarial examples, but these categories do not consistently identify where an adversary first enters the embodied control loop. We present a…

Read at arXiv (research papers)

arXiv (research papers) Zonghao Ying SI

Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection

We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute DSH, collect traces, and judge outcomes. The study covers 14,560 controlled executions over 16 indirect-content channels, text and file carrier modes, 35 payload objectives, one unmodified baseline, and 12 attack methods. The experiment preserves DSH's agent loop, tool registry, model adapter, and session-event path; source tools…

Read at arXiv (research papers)

Older stories